Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ChatGPT in Data Visualization Education: A Student Perspective

Nam Wook Kim, Hyung-Kwon Ko, Grace Myers, Benjamin Bach

TL;DR

This study investigates how undergraduate students use a large-language-model chatbot (ChatGPT) in a project-based data visualization course, examining four distinct assignments and collecting conversation logs, surveys, and interviews to assess benefits, barriers, and learning outcomes. The authors employ multi-method analyses, including open coding of interviews and GPT-assisted thematic analysis of 3,773 queries, to reveal that coding assistance and rapid information access are major advantages, while issues of accuracy, phrasing, and memory limit their effectiveness for design guidance. Across results, students experienced improved efficiency and confidence, yet expressed concerns about overreliance and the need for multimodal, design-focused, and verifiable AI support. The work contributes design-oriented insights for future AI-enhanced learning tools in data visualization, emphasizing student-in-the-loop, equitable, and multimodal interfaces that support both coding tasks and creative data storytelling.

Abstract

Unlike traditional educational chatbots that rely on pre-programmed responses, large-language model-driven chatbots, such as ChatGPT, demonstrate remarkable versatility to serve as a dynamic resource for addressing student needs from understanding advanced concepts to solving complex problems. This work explores the impact of such technology on student learning in an interdisciplinary, project-oriented data visualization course. Throughout the semester, students engaged with ChatGPT across four distinct projects, designing and implementing data visualizations using a variety of tools such as Tableau, D3, and Vega-lite. We collected conversation logs and reflection surveys after each assignment and conducted interviews with selected students to gain deeper insights into their experiences with ChatGPT. Our analysis examined the advantages and barriers of using ChatGPT, students' querying behavior, the types of assistance sought, and its impact on assignment outcomes and engagement. We discuss design considerations for an educational solution tailored for data visualization education, extending beyond ChatGPT's basic interface.

ChatGPT in Data Visualization Education: A Student Perspective

TL;DR

This study investigates how undergraduate students use a large-language-model chatbot (ChatGPT) in a project-based data visualization course, examining four distinct assignments and collecting conversation logs, surveys, and interviews to assess benefits, barriers, and learning outcomes. The authors employ multi-method analyses, including open coding of interviews and GPT-assisted thematic analysis of 3,773 queries, to reveal that coding assistance and rapid information access are major advantages, while issues of accuracy, phrasing, and memory limit their effectiveness for design guidance. Across results, students experienced improved efficiency and confidence, yet expressed concerns about overreliance and the need for multimodal, design-focused, and verifiable AI support. The work contributes design-oriented insights for future AI-enhanced learning tools in data visualization, emphasizing student-in-the-loop, equitable, and multimodal interfaces that support both coding tasks and creative data storytelling.

Abstract

Unlike traditional educational chatbots that rely on pre-programmed responses, large-language model-driven chatbots, such as ChatGPT, demonstrate remarkable versatility to serve as a dynamic resource for addressing student needs from understanding advanced concepts to solving complex problems. This work explores the impact of such technology on student learning in an interdisciplinary, project-oriented data visualization course. Throughout the semester, students engaged with ChatGPT across four distinct projects, designing and implementing data visualizations using a variety of tools such as Tableau, D3, and Vega-lite. We collected conversation logs and reflection surveys after each assignment and conducted interviews with selected students to gain deeper insights into their experiences with ChatGPT. Our analysis examined the advantages and barriers of using ChatGPT, students' querying behavior, the types of assistance sought, and its impact on assignment outcomes and engagement. We discuss design considerations for an educational solution tailored for data visualization education, extending beyond ChatGPT's basic interface.
Paper Structure (45 sections, 3 figures, 1 table)

This paper contains 45 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background & Related Work
  3. Methodology
  4. Procedures
  5. Participants
  6. Survey participants
  7. Interview Participants
  8. Task Assignments
  9. Design & Redesign
  10. Exploration and exposition with Tableau
  11. Interactive Dashboard using D3
  12. Data-Driven Article using D3 & Vega-lite
  13. Data & Analysis Methods
  14. Survey & Interview Analysis
  15. Conversational Log Analysis
  16. ...and 30 more sections

Figures (3)

  • Figure 1: Survey responses from 26 participants on ChatGPT's impact in a data visualization course, encompassing overall experience, assignment quality, engagement, future use intention, and effectiveness in time management across various projects.
  • Figure 2: Intermediate survey results for individual assignments, illustrating satisfaction with support, confidence levels, frequency and helpfulness of ChatGPT interaction, speed of assignment completion, and areas of consultation within specific projects.
  • Figure 3: Three themes extracted from analyzing 3,773 queries from 26 users.